remove conflicting default for tool prompt format in chat completion (#742)

# What does this PR do?
We are setting a default value of json for tool prompt format, which
conflicts with llama 3.2/3.3 models since they use python list. This PR
changes the defaults to None and in the code, we infer default based on
the model.

Addresses: #695 

Tests:
❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/inference/test_inference.py -k
"test_text_chat_completion"

 pytest llama_stack/providers/tests/inference/test_prompt_adapter.py

llama_stack/providers/remote/inference/databricks/databricks.py

@@ -7,11 +7,8 @@
 from typing import AsyncGenerator, List, Optional
 
 from llama_models.datatypes import CoreModelId
-
 from llama_models.llama3.api.chat_format import ChatFormat
-
 from llama_models.llama3.api.tokenizer import Tokenizer
-
 from openai import OpenAI
 
 from llama_stack.apis.common.content_types import InterleavedContent
@@ -28,7 +25,6 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
-
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,
     ModelRegistryHelper,
@@ -44,7 +40,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import DatabricksImplConfig
 
-
 model_aliases = [
     build_model_alias(
         "databricks-meta-llama-3-1-70b-instruct",
@@ -91,7 +86,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
         response_format: Optional[ResponseFormat] = None,
         tools: Optional[List[ToolDefinition]] = None,
         tool_choice: Optional[ToolChoice] = ToolChoice.auto,
-        tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+        tool_prompt_format: Optional[ToolPromptFormat] = None,
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> AsyncGenerator: